Papers by Zeyu Zhang

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)

Challenge:	Existing text-to-SQL systems take a slot-filling approach, but they are limited in capturing inter-dependencies among SQL clauses.
Approach:	They propose an extraction-linking approach where a unified extractor recognizes all types of slot mentions appearing in the question sentence before a linker maps the recognized columns to the table schema to generate executable SQL queries.
Outcome:	The proposed method achieves the first place on the WikiSQL benchmark.

Copied to clipboard

Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang

CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)

Challenge:	PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks.
Approach:	They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks.
Outcome:	The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods.

Copied to clipboard

Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin

Turning the Tide: Repository-based Code Reflection (2025.findings-emnlp)

Challenge:	Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences.
Approach:	They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks.
Outcome:	The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones.

Copied to clipboard

Wei Zhang, Jian Yang, Jiaxi Yang, Ya Wang, Zhoujun Li, Zeyu Cui, Binyuan Hui, Junyang Lin

DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection (2026.acl-long)

Challenge:	Code large language models (LLMs) enhance programming by understanding and generating code across languages.
Approach:	a new benchmark evaluates code understanding and generation in repositories using code large language models.
Outcome:	The proposed model improves code understanding and generation in repositories by evaluating 1,888 test cases across 6 programming languages.

Copied to clipboard

Junchao Wu, Yefeng Liu, Chenyu Zhu, Hao Zhang, Zeyu Wu, Tianqi Shi, Yichao Du, Longyue Wang, Weihua Luo, Jinsong Su, Derek F. Wong

Robustness in NLP

Challenge:	Existing detectors are limited in their ability to detect large language models generated content in multilingual environments.
Approach:	They propose a multilingual benchmark to evaluate advanced detectors across 8 dimensions to better align with real-world applications.
Outcome:	The proposed benchmark encompasses 8 languages commonly used in commercial contexts and collects human-written texts from 6 domains highly susceptible to LLM misuse.

Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries (2024.naacl-short)

Copied to clipboard

Zeyu Zhang, Egoitz Laparra, Steven Bethard

Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution (2023.starsem-1)

Challenge:	Existing approaches to geocoding only encode location mentions and their context .
Approach:	They propose a prompt-based approach to geocoding where the machine learning algorithm encodes only the location mention and its context.
Outcome:	The proposed model achieves state-of-the-art performance on multiple datasets.

Copied to clipboard

Zeyu Zhang, Steven Bethard

Frustratingly Simple Few-Shot Slot Tagging (2021.findings-acl)

Challenge:	Geocoding is the task of converting location mentions in text into structured data that encodes the geospatial semantics.
Approach:	They propose a new architecture that generates a list of geospatial ontologies and reranks them using a transformer-based neural network.
Outcome:	The proposed architecture achieves state-of-the-art on multiple datasets.

Copied to clipboard

Jianqiang Ma, Zeyu Yan, Chang Li, Yang Zhang

A Dashboard for Mitigating the COVID-19 Misinfodemic (2021.eacl-demos)

Challenge:	Existing fewshot methods for slot tagging are weak in encoding slot name semantics and slot dependencies.
Approach:	They propose a simple and effective few-shot model for slot tagging which incorporates machine reading comprehension (MRC) using source domain and target domain data.
Outcome:	The proposed model outperforms state-of-the-art methods on the SNIPS dataset.

Copied to clipboard

Zhengyuan Zhu, Kevin Meng, Josue Caraballo, Israa Jaradat, Xiao Shi, Zeyu Zhang, Farahnaz Akrami, Haojin Liao, Fatma Arslan, Damian Jimenez, Mohanmmed Samiul Saeef, Paras Pathak, Chengkai Li

Reasoning

Challenge:	a new public dashboard aims to understand the impact of the COVID-19 misinfodemic on Twitter . the dashboard uses a curated catalog of COVId-19 related facts and debunks of misinformation .
Approach:	They propose a public dashboard that matches tweets with COVID-19 misinformation . they also propose experiments to analyze the spread of misinformation on twitter .
Outcome:	The proposed dashboard uses a curated catalog of COVID-19 related facts and debunks misinformation . it shows the most prevalent information from the catalog among Twitter users in user-selected geographic regions .

LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media (2025.findings-acl)

Copied to clipboard

Haiqi Zhang, Zhengyuan Zhu, Zeyu Zhang, Chengkai Li

HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification (2024.eacl-long)

Challenge:	Social media's global reach and ease of use have transformed how millions of users exchange opinions, news, and factual claims in real-time, making it fertile ground for misinformation.
Approach:	They propose a framework that leverages large language models to construct taxonomies of factual claims from social media by generating topics at multiple levels of granularity.
Outcome:	The proposed framework produces clear, coherent, and comprehensive taxonomies on three diverse datasets and outperforms other frameworks in most metrics.

Copied to clipboard

Vidit Jain, Mukund Rungta, Yuchen Zhuang, Yue Yu, Zeyu Wang, Mu Gao, Jeffrey Skolnick, Chao Zhang

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models (2026.acl-long)

Challenge:	Hierarchical text classification is a complex subtask under multi-label text classification . the relevance of document sections can vary based on the hierarchy level, necessitating a dynamic document representation.
Approach:	They propose a text-generation-based framework that uses language models to encode dynamic text representations.
Outcome:	The proposed framework surpasses existing methods while handling data and mitigating class imbalance.

Copied to clipboard

Zirui Song, Qian Jiang, Mingxuan Cui, Mingzhe Li, Lang Gao, Zeyu Zhang, Zixiang Xu, Yanbo Wang, Guangxian Ouyang, Zhenhao Chen, Xiuying Chen

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)

Challenge:	a recent study evaluated large audio-language models against jailbreak attacks . a new benchmark is being developed to evaluate LAM safety against jailbreaking attacks based on temporal and semantic nature of speech .
Approach:	They propose a benchmark to evaluate LAM jailbreak vulnerabilities in adversarial audio prompts . they use a dataset of 1,495 adversarials to evaluate their performance .
Outcome:	The proposed benchmark evaluates state-of-the-art LAMs against jailbreak attacks . it demonstrates that even small, semantically preserved perturbations can reduce safety .

Copied to clipboard

Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang

TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System (2025.findings-naacl)

Challenge:	Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps.
Approach:	They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level.
Outcome:	Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models.

Copied to clipboard

Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen

Robustness in NLP

Challenge:	Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach:	They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome:	The proposed system simulates trending topics under poisoning attacks on social media platforms.

PresentAgent: Multimodal Agent for Presentation Video Generation (2025.emnlp-demos)

Copied to clipboard

Jingwei Shi, Zeyu Zhang, Biao Wu, Yanjie Liang, Meng Fang, Ling Chen, Yang Zhao

MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents (2025.findings-acl)

Challenge:	Existing methods for generating static slides or text summaries are limited to producing narrated presentations.
Approach:	They propose a multimodal agent that transforms long-form documents into narrated presentations.
Outcome:	The present agent produces fully synchronized visual and spoken content that closely mimics human-style presentations.

Copied to clipboard

Haoran Tan, Zeyu Zhang, Chen Ma, Xu Chen, Quanyu Dai, Zhenhua Dong

Challenge:	Recent studies have highlighted the significance of memory mechanisms in LLM-based agents, which enable them to store observed information and adapt to dynamic environments.
Approach:	They propose a dataset and benchmark to evaluate the memory capability of LLM-based agents from multiple aspects including their effectiveness, efficiency, and capacity.
Outcome:	The proposed benchmark incorporates factual memory and reflective memory as different levels, and proposes participation and observation as various interactive scenarios.

DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios (2025.findings-acl)

Copied to clipboard

Zeyu Gao, Yuxin Cui, Hao Wang, Siliang Qin, Yuanda Wang, Zhang Bolun, Chao Zhang

Challenge:	Existing approaches focus on syntactic correctness through synthetic micro-benchmarks or subjective human ratings, despite semantic fidelity and usability.
Approach:	They propose a framework that enables effective evaluation of decompilers in reverse engineering workflows . they compare six industrial-strength decompils and six recent LLM-powered approaches .
Outcome:	The proposed framework outperforms commercial tools in code understandability despite lower functionality correctness . it shows that it can transform human-centric reverse engineering workflows .

Joint Models for Answer Verification in Question Answering Systems (2021.acl-long)

Copied to clipboard

Zeyu Zhang, Thuy Vu, Alessandro Moschitti

Information Retrieval

Challenge:	Using a joint approach, we found that the model is more efficient than those developed in machine reading (MR) work.
Approach:	They propose a joint model for selecting correct answer sentences among the top k provided by answer sentence selection modules.
Outcome:	The proposed model improves on WikiQA, TREC-QA, and a real-world dataset.

TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation (2021.findings-emnlp)

Copied to clipboard

Adaku Uchendu, Zeyu Ma, Thai Le, Rui Zhang, Dongwon Lee

ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition (2020.lrec-1)

Challenge:	Recent advances in generative language models have enabled machines to generate realistic texts.
Approach:	They propose a benchmark environment to test the 'Turing Test' problem for neural text generation methods.
Outcome:	The proposed benchmark environment is based on 200K human- or machine-generated samples across 20 labels Human, GPT-1, GTP-2_small, GTT-2_medium, GPG-2_large, GGT-2_PyTorch, GGP-3, GROVER_base, griover_large and GRover_mega.

Copied to clipboard

Hannah Smith, Zeyu Zhang, John Culnan, Peter Jansen

Information Extraction & Text Mining

Challenge:	Named entity recognition identifies common classes of noun phrases in text, but these entity labels are sparse, limiting utility to downstream tasks.
Approach:	They propose a name-based named entity recognition model that annotates all content words with a fine-grained semantic class label.
Outcome:	The proposed model achieves 0.85 F1 on the science exam domain domain . the proposed model is a powerful tool for question answering and inference .

Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies (2026.findings-acl)

Copied to clipboard

Qianen Zhang, Zeyu Yang, Satoshi Nakamura

Text Generation

Challenge:	Simultaneous machine translation requires high-quality translations under strict real-time constraints.
Approach:	They extend the action space of simultaneous machine translation with four adaptive actions . they adapt these actions in a large language model framework and construct training references .
Outcome:	The proposed framework improves semantic metrics and achieves lower delay compared to reference translations and salami-based baselines.

RATSD: Retrieval Augmented Truthfulness Stance Detection from Social Media Posts Toward Factual Claims (2025.findings-naacl)

Copied to clipboard

Zhengyuan Zhu, Zeyu Zhang, Haiqi Zhang, Chengkai Li

Sentiment Analysis

Challenge:	Social media provides a valuable lens for assessing public perceptions and opinions.
Approach:	They propose a method that leverages large language models with retrieval-augmented generation to analyze tweets in relation to claims.
Outcome:	The proposed method outperforms state-of-the-art methods on a new dataset . it shows that it outperformed existing methods and achieves a significant increase in Macro-F1 score on TSD-CT.

Double Retrieval and Ranking for Accurate Question Answering (2023.findings-eacl)

Copied to clipboard

Zeyu Zhang, Thuy Vu, Alessandro Moschitti

Natural Language Interfaces

Challenge:	Recent work shows that answer verification models can improve the state of the art in Question Answering . despite the fact that the supporting candidates are ranked only according to the relevancy with the question, the model still lacks the support needed for other answer candidates.
Approach:	They propose a double reranking model that selects the best support for each target answer . they propose 'second neural retrieval stage' to encode question and answer pair as query .
Outcome:	The proposed approach improves the state of the art in Question Answering . the proposed model ranked candidates according to relevancy and not the answer . but the proposed approach fails to provide the best support .

Hallucination Mitigation in Natural Language Generation from Large-Scale Open-Domain Knowledge Graphs (2023.emnlp-main)

Copied to clipboard

Xiao Shi, Zhengyuan Zhu, Zeyu Zhang, Chengkai Li

Structured Data in NLP

Challenge:	Graph-to-text models trained on small-scale datasets or datasets with limited variety of graph shapes are not adequate for more realistic large-scale, open-domain settings.
Approach:	They propose a novel approach that, given a graph-sentence pair in GraphNarrative, trims the sentence to eliminate portions that are not present in the corresponding graph.
Outcome:	The proposed model can be trained on existing datasets and is available on github.

SQL Generation via Machine Reading Comprehension (2020.coling-main)

Copied to clipboard

Zeyu Yan, Jianqiang Ma, Yang Zhang, Jianping Shen

From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents (2026.findings-acl)

Challenge:	Text-to-SQL systems can generate SQL queries given natural language questions.
Approach:	They propose a method that formulates a question answering problem as a query answering problem where different slots are predicted by a unified machine reading comprehension (MRC) model.
Outcome:	The proposed method can achieve competitive results on WikiSQL, suggesting it being a promising direction for text-to-SQl.

Copied to clipboard

Haoran Tan, Zeyu Zhang, Chen Ma, Tianze Liu, Quanyu Dai, Xu Chen

Challenge:	Existing plans for large language model-based agents are limited by their granularity and lack flexibility.
Approach:	They propose a self-adaptive hierarchical planning mechanism that mimics human planning strategies and generates self-adapted hierarchic plans tailored to the varying difficulty levels of different tasks.
Outcome:	The proposed method significantly improves task execution success rates while mitigating overthinking at the planning level, providing a flexible and efficient solution for multi-step complex decision-making tasks.

Virtual Compiler Is All You Need For Assembly Code Search (2024.acl-long)

Copied to clipboard

Zeyu Gao, Hao Wang, Yuanda Wang, Chao Zhang

VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery (2026.findings-eacl)

Challenge:	Using a large dataset, we find that assembly code search is a significant task for reverse engineers.
Approach:	They propose to train a Large Language Model (LLM) to emulate a general compiler.
Outcome:	The proposed model surpasses the baseline by 26%.

Copied to clipboard

Jinchao Ge, Tengfei Cheng, Biao Wu, Zeyu Zhang, Shiya Huang, Judith Bishop, Gillian Shepherd, Meng Fang, Ling Chen, Yang Zhao

Retrieving Support to Rank Answers in Open-Domain Question Answering (2025.emnlp-main)

Challenge:	MLLMs that use domain-specific data are limited in understanding cultural heritage artifacts such as ancient Greek pottery . supervised fine-tuning improves adaptation to domain knowledge, but it struggles with deeper reasoning tasks.
Approach:	They propose a visual question-answer tool that augments SFT with reinforcement learning using verifiable rewards.
Outcome:	The proposed model outperforms baseline models on reasoning-intensive questions on ancient Greek pottery.

Copied to clipboard

Zeyu Zhang, Alessandro Moschitti, Thuy Vu

Information Retrieval

Challenge:	a novel question answering architecture retrieves content relevant to the combined pair . previous work on automatic claim verification has shown hallucinations .
Approach:	They propose a question-answer architecture that prioritizes supporting evidence . it retrieves paragraphs that directly substantiate the correctness of a with respect to q .
Outcome:	The proposed approach can be used by large language models to retrieve explanatory paragraphs that ground their reasoning.

CoV: Chain-of-View Prompting for Spatial Reasoning (2026.findings-acl)

Copied to clipboard

Haoyu Zhao, Akide Liu, Zeyu Zhang, Weijie Wang, Feng Chen, Ruihan Zhu, Gholamreza Haffari, Bohan Zhuang

Low-Resource NLP

Challenge:	Embodied question answering requires collecting context that is distributed across multiple viewpoints . most recent vision–language models (VLMs) are constrained to a fixed and finite set of input views .
Approach:	They propose a training-free, test-time reasoning framework that transforms a VLM into an active viewpoint reasoner through a coarse-to-fine exploration process.
Outcome:	The proposed framework improves LLM-Match performance by 11.98% on four mainstream VLMs.

MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training (2026.acl-long)

Copied to clipboard

Biao Wu, Yutong Xie, Zeyu Zhang, Vu Minh Hieu Phan, Qi Chen, Ling Chen, Qi Wu

Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies (2025.naacl-long)

Challenge:	Existing vision-and-language pretraining methods face challenges in reconstructing pathological features due to limited data.
Approach:	They propose a method that uses masked modeling to enhance visual and linguistic learning.
Outcome:	MMCLIP integrates unpaired data through disease-kind prompts to achieve state-of-the-art performance in zero-shot and fine-tuning across five benchmarks.

Copied to clipboard

Zirui Song, Guangxian Ouyang, Meng Fang, Hongbin Na, Zijing Shi, Zhenhao Chen, Fu Yujie, Zeyu Zhang, Shiyu Jiang, Miao Fang, Ling Chen, Xiuying Chen

Challenge:	Existing household robots are inability to recognize potential problems or dangers in home environments.
Approach:	They propose a task of creating anomaly scenarios using generative models instead of manually labeled data to build simulated environments.
Outcome:	The proposed framework outperforms existing models in terms of task description and scene diversity.

FASTMATCH: Accelerating the Inference of BERT-based Text Matching (2020.coling-main)

Copied to clipboard

Shuai Pang, Jianqiang Ma, Zeyu Yan, Yang Zhang, Jianping Shen

Qwen2.5-xCoder: Multi-Agent Collaboration for Multilingual Code Instruction Tuning (2025.acl-long)

Challenge:	Recent pre-trained language models have shown state-of-the-art accuracies in text matching.
Approach:	They propose a BERT-based text matching model where representations and interactions are decoupled . they propose generating final matching scores using a lightweight attention network .
Outcome:	Experiments show that the proposed model can achieve up to 100X speed-up to BERT and RoBERTa while keeping more up to 98.7% of the performance.

Copied to clipboard

Jian Yang, Wei Zhang, Yibo Miao, Shanghaoran Quan, Zhenhe Wu, Qiyao Peng, Liqun Yang, Tianyu Liu, Zeyu Cui, Binyuan Hui, Junyang Lin

A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization (2020.acl-main)

Challenge:	Existing methods to train code LLMs view each programming language in isolation . experimental results show that Qwen2.5-xCoder can bridge the gap between different programming languages .
Approach:	They propose a framework that allows agents to collaborate to enhance multilingual instruction tuning for code LLMs.
Outcome:	Experimental results show that Qwen2.5-xCoder can transfer knowledge efficiently and effectively between languages.

Copied to clipboard

Dongfang Xu, Zeyu Zhang, Steven Bethard

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs? (2025.findings-acl)

Challenge:	Concept normalization is a task that maps textual mentions of concepts to concepts in an ontology . lexical and grammatical variations are pervasive in such text, posing key challenges for data interoperability and the development of natural language processing (NLP) techniques.
Approach:	They propose a concept normalization framework that uses a candidate generator and a list-wise ranker to link concept mentions to concepts in an ontology.
Outcome:	The proposed framework achieves state-of-the-art performance on multiple datasets.

Copied to clipboard

Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Xiao Yueyi, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Chenbin Chenbin, Yingfei Xiong

ARXSA: A General Negative Feedback Control Theory in Vision-Language Models (2025.findings-emnlp)

Challenge:	Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance.
Approach:	They develop a series of billion-scale grammar-based code representations that incorporate grammar rules into the code generation process.
Outcome:	Experiments on HumanEval and MBPP show that grammar-based representations reduce syntax errors and improve performance even in billion-scale models.

Copied to clipboard

Zeyu Zhang, Tianqi Chen, Yuki Todo

KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)

Challenge:	a new approach to the self-attention mechanism is proposed for integrating data from multiple batches.
Approach:	They propose an autoregressive with exogenous inputs approach for the Transformer model . the proposed method transforms the Encoder block into a negative feedback predictive control system .
Outcome:	The proposed method is validated through comparative evaluations.

Copied to clipboard

Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zeyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong

DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation (2025.findings-acl)

Challenge:	Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge.
Approach:	They propose a benchmark to evaluate domain specialization methods in real-world software development.
Outcome:	KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development.

Copied to clipboard

Zhonghao Sun, Zhiliang Tian, Yiping Song, Yuyi Si, Juhua Zhang, Minlie Huang, Kai Lu, Zeyu Xiong, Xinwang Liu, Dongsheng Li

Ethical NLP

Challenge:	Existing methods to fine-tune large language models pose privacy risks . researchers have synthesized data with strong generation capabilities closed-source LLMs to alleviate this problem .
Approach:	They propose to combine general LLMs with genetic algorithm to produce relevant and diverse synthetic text under differential privacy constraints.
Outcome:	The proposed method significantly improves the performance of the model in downstream tasks while ensuring privacy.

CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data (2026.acl-long)

Copied to clipboard

Zeyu Zhang, Kexuan Sun, Zheng Tang, Jens-S. Vöckler, Thien Huu Nguyen, Thuy Vu

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem (2026.findings-acl)

Challenge:	Existing datasets are small, domain-limited, and lack diversity, constraining LLM progress.
Approach:	They propose a knowledge Graph retrieval tool that can translate natural language questions into structured queries.
Outcome:	Extensive experiments show that CypherSmith achieves state-of-the-art performance.

Copied to clipboard

Chengyou Wang, Mingchen Shao, Jingbin Hu, Zeyu Zhu, Hongfei Xue, Bingshen Mu, Xin Xu, Xingyi Duan, Binbin Zhang, Zhu Pengcheng, Chuang Ding, Xiaojun Zhang, Hui Bu, Lei Xie

Mixture of Attention Heads: Selecting Attention Heads Per Token (2022.emnlp-main)

Challenge:	despite its linguistic significance, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models.
Approach:	They propose to use WenetSpeech-Wu as a large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect of Chinese.
Outcome:	The proposed dataset includes 8,000 hours of speech data and strong open-source models . the proposed dataset is competitive and empirically validated .

Copied to clipboard

Xiaofeng Zhang, Yikang Shen, Zeyu Huang, Jie Zhou, Wenge Rong, Zhang Xiong

Responsible & Trustworthy NLP

Challenge:	Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing.
Approach:	They propose a new architecture that combines multi-head attention with the MoE mechanism and a sparsely gated architecture that allows for faster computations.
Outcome:	The proposed architecture can scale up the number of attention heads and the number parameters while preserving computational efficiency.

A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage (2026.acl-long)

Copied to clipboard

Congmin Zheng, Jiachen Zhu, Zhuoying Ou, Yuxiang Chen, Kangning Zhang, Rong Shan, Zeyu Zheng, Mengyue Yang, Jianghao Lin, Yong Yu, Weinan Zhang

Reasoning

Challenge:	Large Language Models (LLMs) have advanced reasoning ability, yet conventional alignment remains dominated by outcome reward models that judge only final answers.
Approach:	They summarize applications across math, code, text, multimodal reasoning, robotics, and agents . goal is to clarify design spaces, reveal open challenges, and guide future research toward fine-grained, robust reasoning alignment.
Outcome:	The proposed model enables finer credit assignment, richer diagnostics, and improved robustness.

From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning (2026.acl-long)

Copied to clipboard

Jiajun Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Yuheng Jing, Zeyao Ma, Tianyi Bai, Zilei Wang, Qiang Liu, Liang Wang, Binyuan Hui, Junyang Lin